Regression-Based Approach to Anxiety Estimation of Spider Phobics During Behavioural Avoidance Tasks

TL;DR

This study develops a regression model using physiological data from wrist sensors to continuously estimate anxiety levels in spider phobics during behavioral avoidance tasks, enhancing personalized therapy options.

Contribution

It introduces a novel approach combining physiological signals and contextual data to accurately predict anxiety in real-time during BATs.

Findings

Adding contextual information improves model accuracy.

The model achieved RMSE of 0.197 and MAE of 0.041.

Wearable sensors can effectively monitor anxiety levels continuously.

Abstract

Phobias significantly impact the quality of life of affected persons. Two methods of assessing anxiety responses are questionnaires and behavioural avoidance tests (BAT). While these can be used in a clinical environment they only record momentary insights into anxiety measures. In this study, we estimate the intensity of anxiety during these BATs, using physiological data collected from unobtrusive, wrist-worn sensors. Twenty-five participants performed four different BATs in a single session, while periodically being asked how anxious they currently are. Using heart rate, heart rate variability, electrodermal activity, and skin temperature, we trained regression models to predict anxiety ratings from three types of input data: (1) using only physiological signals, (2) adding computed features (e.g., min, max, range, variability), and (3) computed features combined with contextual task information. Adding contextual information increased the effectiveness of the model, leading to a root mean squared error (RMSE) of 0.197 and a mean absolute error (MAE) of 0.041. Overall, this study shows, that data obtained from wearables can continuously provide meaningful estimations of anxiety, which can assist in therapy planning and enable more personalised treatment.